We are Geely Technology Europe. A unified European R&D centre within Geely Auto Group, where world-class engineers, developers and innovators push the boundaries of intelligent mobility. Our mission is to shape the next generation of vehicle architectures, digital technologies and intelligent systems for global markets. We integrate European customer and regulatory requirements early in the development process and support multiple brands within the Geely portfolio, including Zeekr, Lynk & Co and Geely. With nearly two decades of engineering experience in Europe, we continue to build smart, sustainable and user‑centric mobility solutions.
Project Description:
Battery electric vehicle energy consumption is influenced by multiple factors, including route characteristics, driving conditions, vehicle states, environmental conditions, and driver behaviors. Reliable energy prediction is important for trip planning, range estimation, charging decisions, and improving the overall EV user experience.
A particular challenge is that the information available before a trip differs from the observations available during driving. Pre-trip prediction must rely mainly on planned route and contextual information, while during the trip, actual vehicle and driving observations become available and can be used to continuously refine the estimate. Developing a prediction approach that can bridge these two stages is therefore an important practical problem.
This thesis will investigate data-driven approaches for pre-trip energy prediction and dynamic remaining-energy prediction. The project will have access to open datasets as well as large-scale internal data collected from company test vehicles. The internal vehicle data will require substantial preprocessing, data quality analysis, feature engineering, and construction of suitable training and evaluation datasets before modelling.
The project is expected to develop and evaluate suitable modelling approaches for pre-trip and dynamic remaining-energy prediction, and to compare the proposed models against established baseline or benchmark methods.
Scope:
The thesis will focus on energy prediction at the trip and remaining-trip level for battery electric vehicles. The work includes data exploration and preprocessing, feature engineering, model development, and quantitative evaluation.
Both public/open datasets and company-provided test-vehicle data may be used. A significant part of the project will involve understanding and processing large-scale real-world vehicle data and establishing a reliable dataset for model development and evaluation. The project will also investigate a modelling framework that combines pre-trip energy prediction with online adaptation based on observations collected during driving. A potential direction is to use a data-driven nominal energy model together with an online state-estimation or residual-adaptation mechanism to dynamically update the remaining-energy prediction. The exact model architecture and implementation may be refined based on the characteristics of the available data and findings during the project.
Objective:
The objective of the thesis is to develop and evaluate a data-driven approach that can:
estimate expected energy consumption before a trip based on available route, vehicle, and contextual information;
update the remaining-energy estimate dynamically as new observations become available during driving;
evaluate prediction accuracy, robustness, and interpretability under different driving scenarios and data conditions;
investigate how pre-trip estimates and online observations can be effectively integrated into a unified prediction framework.
Expected outcomes:
A structured and reliable dataset for EV energy prediction, constructed from open datasets and large-scale internal test-vehicle data.
A pre-trip energy prediction model using route, vehicle, and contextual information.
A dynamic remaining-energy prediction approach that updates estimates using observations collected during driving.
A proposed modelling framework that integrates pre-trip prediction with online adaptation or state estimation.
Quantitative evaluation of the proposed approach against relevant baseline or benchmark methods in terms of prediction accuracy, robustness, and interpretability.
Analysis of the factors that most strongly influence prediction performance under different driving conditions.
A final thesis report documenting the methodology, experiments, results, limitations, and recommendations for future development.
Your skills and background
Suitable for Master’s students in Computer Science, Data Science, Machine Learning, Automotive Engineering, Electrical Engineering, or related fields.
Strong programming skills in Python and solid knowledge of machine learning are required.
Experience with large-scale data processing, data preprocessing, feature engineering, and handling real-world datasets is highly desirable.
Experience with deep learning, time-series or sequential modelling, statistical modelling, and data-driven model evaluation is highly desirable.
Familiarity with probabilistic modelling, online learning, or vehicle energy modelling is considered an advantage.
Why you should join Geely Tech Eu
We are engineers, developers, and innovators from around the world. Joined together by entrepreneurship, our unique blend of global culture, and a belief in a smarter more sustainable future. At Geely Tech Eu we fast-track innovation and transform ideas into pioneering technology solutions, doing your master thesis here is no different. We are convinced that a thesis project is a major contribution to our innovation capabilities and long-term development. You'll have a great opportunity to use your skills and creativity to push the boundaries of what´s possible.
What happens when you apply
If this sounds interesting and you match the requirements, please don't hesitate to submit your application with a CV and cover letter. Shortlisted candidates will be contacted for an interview to further discuss the project's details and expectations.
This thesis project is intended for 1-2 students. Applicants may specify a preferred partner in their cover letter.
Supervisor: Yuchuan Dong, AI Engineer,yuchuan.dong1@zeekrtech.eu, please contact for more information about the project
Starting date: January 2027
Last application date: 2026-10-31
Apply today. We will perform ongoing selection during the application period. We look forward to hearing from you!
Please note that due to GDPR regulations, we can only accept applications sent through the recruitment system, not via email or other channels.
